Alzheimer’s disease is a progressive neurodegenerative disorder that affects memory, cognition, and behavior. Advances in AI technology, particularly in deep learning and medical imaging, offer powerful tools for early detection and classification of Alzheimer’s disease, improving diagnosis and treatment outcomes. In this preliminary research, the authors aimed to highlight the impact of selected digital data on various preprocessing techniques for the classification of Alzheimer’s disease. They also highlight the potential challenges of implementing the FreeSurfer ‘recon-all’ module in healthcare applications. Data collection plays a crucial role in standardizing images for consistent analysis. The authors developed and evaluated three different preprocessing strategies using a custom EfficientNetV2S architecture. The results indicate that more complex preprocessing steps, such as skull stripping, lead to improved classification precision. However, technical challenges such as long processing times and FreeSurfer’s closed-code environment limit its practicality in fast-paced healthcare settings. The hypothesis suggests that skull-stripped MRI sequences processed through FreeSurfer offer a more accurate method of detecting Alzheimer’s than alternative strategies. The findings of this preliminary research support this hypothesis, with skull stripping showing better accuracy. However, the differences between methods are minimal given the current data set and the set-up of the selected model. Future research should focus on expanding the dataset and enhancing model robustness by performing a comparative study with other architectures like ResNet, ViT, or hybrid models, which could further highlight the potential advantages of skull-stripping for Alzheimer’s detection.